Despite the vast quantities of published artificial intelligence (AI) algorithms that target trauma and orthopaedic applications, very few progress to inform clinical practice. One key reason for this is the lack of a clear pathway from development to deployment. In order to assist with this process, we have developed the Clinical Practice Integration of Artificial Intelligence (CPI-AI) framework – a five-stage approach to the clinical practice adoption of AI in the setting of trauma and orthopaedics, based on the IDEAL principles ( Cite this article:
We evaluated the quality of guidelines on thromboprophylaxis
in orthopaedic surgery by examining how they adhere to validated
methodological standards in their development. A structured review
was performed for guidelines that were published between January
2005 and April 2013 in medical journals or on the Internet. A pre-defined
computerised search was used in MEDLINE, Scopus and Google to identify
the guidelines. The AGREE II assessment tool was used to evaluate
the quality of the guidelines in the study. Seven international and national guidelines were identified.
The overall methodological quality of the individual guidelines
was good. ‘Scope and Purpose’ (median score 98% interquartile range
(IQR)) 86% to 98%) and ‘Clarity of Presentation’ (median score 90%,
IQR 90% to 95%) were the two domains that received the highest scores. ‘Applicability’
(median score 68%, IQR 45% to 75%) and ‘Editorial Independence’
(median score 71%, IQR 68% to 75%) had the lowest scores. These findings reveal that although the overall methodological
quality of guidelines on thromboprophylaxis in orthopaedic surgery
is good, domains within their development, such as ‘Applicability’
and ‘Editorial Independence’, need to be improved. Application of
the AGREE II instrument by the authors of guidelines may improve
the quality of future guidelines and provide increased focus on
aspects of methodology used in their development that are not robust. Cite this article: Bone Joint J 2014;96-B:19–23.
Cite this article:
We performed a systematic review and meta-analysis
to compare the efficacy of intermittent mechanical compression combined
with pharmacological thromboprophylaxis, against either mechanical
compression or pharmacological prophylaxis in preventing deep-vein
thrombosis (DVT) and pulmonary embolism in patients undergoing hip
or knee replacement. A total of six randomised controlled trials,
evaluating a total of 1399 patients, were identified. In knee arthroplasty,
the rate of DVT was reduced from 18.7% with anticoagulation alone
to 3.7% with combined modalities (risk ratio (RR) 0.27, p = 0.03;
number needed to treat: seven). There was moderate, albeit non-significant,
heterogeneity (I2 = 42%). In hip replacement, there was
a non-significant reduction in DVT from 8.7% with mechanical compression
alone to 7.2% with additional pharmacological prophylaxis (RR 0.84)
and a significant reduction in DVT from 9.7% with anticoagulation
alone to 0.9% with additional mechanical compression (RR 0.17, p
<
0.001; number needed to treat: 12), with no heterogeneity (I2 =
0%). The included studies had insufficient power to demonstrate
an effect on pulmonary embolism. We conclude that the addition of intermittent mechanical leg
compression augments the efficacy of anticoagulation in preventing
DVT in patients undergoing both knee and hip replacement. Further
research on the role of combined modalities in thromboprophylaxis
in joint replacement and in other high-risk situations, such as fracture
of the hip, is warranted.
The risk of venous thromboembolism in patients following arthroplasty may be reduced by continuing chemical thromboprophylaxis for up to 35 days post-operatively. This prospective cohort study investigated the compliance of 40 consecutive consenting patients undergoing lower limb arthroplasty with self-administration of a recommended subcutaneous chemotherapeutic agent for six weeks after surgery. Compliance was assessed by examination of the patient for signs of injection, number of syringes used, and a self-report diary at the end of the six-week period. A total of 40 patients, 15 men and 25 women, were recruited. One woman was excluded because immediate post-operative complications prevented her participation. Self-administration was considered feasible in 87% of patients (95% confidence interval (CI) 76 to 98) at the time of discharge. Among this group of 34 patients, 29 (85%) were compliant (95% CI 73 to 97). Patients can learn to self-administer subcutaneous injections of thromboprophylaxis, and compliance with extended prophylaxis to six weeks is good.
We present seven patients with recurrent haemarthroses after total knee arthroplasty, caused by an inherent platelet function defect. These patients developed painful knee swelling, persistent bleeding and/or wound breakdown, a platelet factor 3 availability defect being identified in all cases. Surgical exploration, with joint debridement, lavage and synovectomy, was performed in four patients who did not improve with conservative therapy. Histopathological examination of synovium revealed a focal synovial reaction with histiocytic infiltration, and occasional foreign-body giant cells. One patient required an early revision because of aseptic loosening of their tibial component. The condition was treated by single-donor platelet transfusions with good results. The diagnosis, management, and relevance of this disorder are discussed.